For the data challenge of the 2022 European PHM conference, data from a production line of electric circuit boards is provided to assess the quality of the produced components. The solution presented in this paper was elaborated to fulfill the data challenge objectives of predicting defects found in an automatic inspection at the end of the production line, predicting the result of a following human inspection and predicting the result of the repair of the defect components. Machine learning methods are used to accomplish the different prediction tasks. In order to build a reliable machine learning model, the steps of data preparation, feature engineering and model selection are performed. Finally, different models are chosen and implemented for the different sub-tasks. The prediction of defects in the automatic inspection is modeled with a multi-layer perceptron neural network, the prediction of human inspection is modeled using a random forest algorithm. For the prediction of human repair, a decision tree is implemented.
Health and usage monitoring systems (HUMS) are the basis for condition-based maintenance of helicopters. One of the most critical systems in terms of safety and maintenance expense that can be monitored by HUMS are the main gearboxes of helicopters with turbine engines. While the health monitoring part of HUMS aims to model the health state from the collected sensor data with advanced algorithms, such as machine learning, the usage monitoring part tracks the time of use and operating parameters of the system, such as load, to determine lifetime consumption. In the presented work, a combination of automatic dependent surveillance-broadcast (ADS-B) flight data with a generic helicopter performance model is used to acquire torque profiles of the gearboxes. With damage accumulation methods, the load spectra are transformed to aggregated indicators that reflect the individual gearbox usage. The methodology is applied to samples of two helicopters from a five-year ADS-B data set of German helicopter emergency medical services (HEMS) acquired for the study. The results demonstrate the feasibility of the generic approach, which can support maintenance scheduling and new usage-based maintenance services independent of direct access to installed HUMS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.